Perl 6 - the future is here, just unevenly distributed

IRC log for #gluster-dev, 2017-02-17

| Channels | #gluster-dev index | Today | | Search | Google Search | Plain-Text | summary

All times shown according to UTC.

Time Nick Message
00:20 msvbhat joined #gluster-dev
00:21 vbellur joined #gluster-dev
02:48 ilbot3 joined #gluster-dev
02:48 Topic for #gluster-dev is now Gluster Development Channel - http://gluster.org | For general chat go to #gluster | Patches - http://review.gluster.org/ | Channel Logs - https://botbot.me/freenode/gluster-dev/ & http://irclog.perlgeek.de/gluster-dev/
03:20 h4xr joined #gluster-dev
03:26 Shu6h3ndu joined #gluster-dev
03:28 Shu6h3ndu joined #gluster-dev
03:37 atinm joined #gluster-dev
03:39 nbalacha joined #gluster-dev
03:42 magrawal joined #gluster-dev
03:57 gyadav joined #gluster-dev
04:00 nigelb I wonder what's wrong with tiering on the cage machines.
04:04 nbalacha nigelb, why?
04:04 itisravi joined #gluster-dev
04:04 nbalacha nigelb, whats happening?
04:04 nigelb nbalacha: They fail consistently and I'm 99% sure there's something missing on that machine's setup.
04:04 nigelb https://build.gluster.org/job/cage-test/
04:04 nigelb https://build.gluster.org/job/cage-test/91/console
04:05 nbalacha arent they bad tests ?
04:05 nbalacha or has hari's patch been merged?
04:05 deepbook5broo joined #gluster-dev
04:05 deepbook5broo left #gluster-dev
04:05 nigelb This is not a code problem.
04:05 nigelb I mean, it could be a race condition that the cage machines are faster or slower.
04:07 nbalacha volume tier detach start: failed: Found stopped brick builder2.rht.gluster.org:/d/backends/patchy4
04:07 nbalacha I'll take a look in the evening - I won't be free until then
04:08 nigelb I'll take a look and see if I can find anything problematic :)
04:08 nigelb There's no urgency to fix this up.
04:15 Humble joined #gluster-dev
04:18 nbalacha nigelb, sure.
04:20 mchangir joined #gluster-dev
04:20 kdhananjay joined #gluster-dev
04:22 ppai joined #gluster-dev
04:35 atinm joined #gluster-dev
04:41 nbalacha joined #gluster-dev
04:51 jiffin joined #gluster-dev
04:59 skumar joined #gluster-dev
05:00 sanoj joined #gluster-dev
05:08 rafi joined #gluster-dev
05:08 rjoseph joined #gluster-dev
05:13 karthik_us joined #gluster-dev
05:16 ndarshan joined #gluster-dev
05:21 apandey joined #gluster-dev
05:25 h4xr joined #gluster-dev
05:37 apandey joined #gluster-dev
06:04 Humble joined #gluster-dev
06:06 Saravanakmr joined #gluster-dev
06:08 asengupt joined #gluster-dev
06:17 h4xr joined #gluster-dev
06:38 Byreddy joined #gluster-dev
06:58 msvbhat joined #gluster-dev
07:07 ShwethaHP joined #gluster-dev
07:17 susant joined #gluster-dev
07:22 ankitr joined #gluster-dev
07:26 atinm joined #gluster-dev
07:30 ankitr_ joined #gluster-dev
07:41 msvbhat joined #gluster-dev
08:04 nbalacha joined #gluster-dev
08:12 susant joined #gluster-dev
08:14 pkalever joined #gluster-dev
08:31 atinm joined #gluster-dev
08:40 sanoj joined #gluster-dev
08:45 vimal joined #gluster-dev
08:50 sanoj joined #gluster-dev
08:54 apandey joined #gluster-dev
09:15 poornima joined #gluster-dev
09:17 ndevos anoopcs: do you have any objections to getting https://review.gluster.org/16639 merged? (gf_recon linking fix)
09:17 ndevos anoopcs: if there are other parts that could use improvements, we can send more changes specific to those
09:17 ton31337 joined #gluster-dev
09:18 ton31337 [2017-02-16 16:26:05.781245] E [MSGID: 115068] [server-rpc-fops.c:1440:server_readv_cbk] 0-backup-xxx-server: 666631: READV -2 (0ff1d260-5499-405e-8f7e-2134caffa4fd), client: uk-m247-web45.xxx.eu-111930-2017/01/27-2​2:56:14:292246-backup-xxx-client-10-2-0, error-xlator: backup-xxx-posix [Invalid argument]
09:18 ton31337 i have those time to time
09:18 ton31337 anything to add?
09:18 ndevos anoopcs: and i think doing build tests on Debian would be good, that seems to have most strict requirements/checks
09:18 h4xr joined #gluster-dev
09:20 chawlanikhil24 joined #gluster-dev
09:21 ndevos ton31337: I think that means reading the file with gfid=0ff1d260-5499-405e-8f7e-2134caffa4fd failed, you could check on the brick if it is there
09:21 anoopcs ndevos, Ok. I agree. Go on...
09:22 ashiq joined #gluster-dev
09:23 ndevos anoopcs: thanks, I think we should inspect many makefiles and see if there are unneeded things, like some -D... options - and make 'make V=1' work
09:24 ndevos so, in case you're bored ;-)
09:25 * anoopcs coughs...
09:26 ton31337 ndevos: strange, but it exists
09:35 h4xr_ joined #gluster-dev
09:42 rafi2 joined #gluster-dev
09:43 nbalacha joined #gluster-dev
09:49 vimal joined #gluster-dev
10:00 mchangir joined #gluster-dev
10:06 percevalbot joined #gluster-dev
10:32 mchangir joined #gluster-dev
10:35 atinm joined #gluster-dev
10:36 atinm ndevos, kdhananjay has added a comment in the bug for https://review.gluster.org/#/c/16577/
10:36 atinm ndevos, is that sufficient for you to revert your -1 ?
10:37 ndevos atinm: yes, that is fine
10:37 atinm ndevos, thanks!
10:37 ndevos atinm: do you know if those group option files allow comments?
10:38 atinm ndevos, it may not as we just iterate over the file & read in text format
10:39 atinm ndevos++
10:39 glusterbot atinm: ndevos's karma is now 335
10:39 ndevos atinm: oh, hmm, that would be a shame, I *strongly* recommend to have a comment for all options, it makes it so much easier to understand the reasoning (special with magic numbers)
10:44 itisravi ndevos: would you mind merging https://review.gluster.org/#/c/16621/ without a +1 from pranith? It is a straight forward backport.
10:44 * itisravi can't get hold of pranith to give a vote.
10:51 ndevos atinm, samikshan, kshlm: I hope you guys can track this and improve the user experience a little more - https://bugzilla.redhat.co​m/show_bug.cgi?id=1423442
10:51 glusterbot Bug 1423442: medium, high, ---, bugs, NEW , group files to set volume options should have comments
10:51 rafi joined #gluster-dev
10:52 atinm ndevos, we track each and every glusterd bugs, don't worry ;)
10:52 ndevos itisravi: the next 3.8 release is planned for March 10, what is the need to get it merged now alread?
10:52 ndevos +y
10:53 ndevos atinm: hehe, yes, but it does not hurt to make a little noise about it, and if you have questions about it, I can answer them now while it is fresh in my memory :)
10:54 k4n0 joined #gluster-dev
10:54 itisravi ndevos: If it is March 10, there is no urgency. It is just that I get itchy if a backport has passed regressions and is just sitting there waiting to be merged.
10:57 ndevos itisravi: ok, I tend to wait with checking 3.8 changes that are not in my components until the release date gets closer
10:57 itisravi ndevos: sure no problemo :)
10:59 poornima ndevos, Can you please reply on patch https://review.gluster.org/#/c/16622/   thanks
11:10 ndevos poornima: thanks, can you add that note in the BZ as well?
11:13 msvbhat joined #gluster-dev
11:14 poornima ndevos, sure
11:16 jiffin joined #gluster-dev
11:18 rraja joined #gluster-dev
11:31 ashiq joined #gluster-dev
11:51 shyam poornima: There? Does this https://bugzilla.redhat.co​m/show_bug.cgi?id=1423385 seem to be the same as https://bugzilla.redhat.co​m/show_bug.cgi?id=1423065 (at least the part in AFR that is causing the crash?), just checking, Ravi is on it anyway
11:51 glusterbot Bug 1423385: unspecified, unspecified, ---, pgurusid, POST , Crash in index xlator because of race in inode_ctx_set and inode_ref
11:51 glusterbot Bug 1423065: unspecified, unspecified, ---, ravishankar, ASSIGNED , Deadlock in gf_timer calls and a possible core (illegal memory access) in AFR on dropping FUSE cache
11:52 poornima shyam, yes they look similar
11:54 shyam poornima: Can you point me to stacks for the former bug, just for my reference?
11:54 shyam I can retest with your fix as well sometime today (I hope)
11:56 shyam poornima: and thanks for marking the 3.10 backports with a -1 awaiting merge on master :)
11:57 poornima shyam, Actually Pranith RCAed, verified and debugged it. I do not have the crash bt, also the crash that he debugged was a server side crash.., But the scenario is that the inode ctx of xl1 can end up pointing to inode ctx o xl2.
11:58 poornima shyam, wanted the backport so that atleast the regressions are run. wc:)
11:58 shyam Hmmm... ok will test with your fix, I hit it 2 of 2 times in my test, so maybe this happens always in my test, itsravi is also looking into it anyway...
11:59 ton31337 where can i find this? http://www.gluster.org/community/documentati​on/index.php/Features/Feature_Smallfile_Perf
12:00 poornima shyam, ahh ok
12:00 shyam ton31337: This is another source: https://github.com/gluster/glusterf​s-specs/blob/master/done/GlusterFS%​203.7/Small%20File%20Performance.md not sure if it was the same as the doc you refer to (but should be pretty close)
12:00 ton31337 thanks
12:01 ton31337 i'm looking how to turn multi-thread-epoll
12:02 shyam client.event-threads and server.event-threads are the settings, check "gluster volume get <volname> all | grep event", that should tell you the exact setting name (in case I am goofing it up)
12:02 ton31337 +1
12:07 Saravanakmr joined #gluster-dev
12:14 k4n0 joined #gluster-dev
13:11 pkalever left #gluster-dev
13:17 susant left #gluster-dev
13:21 shyam joined #gluster-dev
13:32 ira joined #gluster-dev
13:36 k4n0 joined #gluster-dev
13:46 shyam joined #gluster-dev
13:48 vbellur left #gluster-dev
14:05 rraja joined #gluster-dev
14:28 vbellur joined #gluster-dev
14:35 gyadav joined #gluster-dev
14:36 msvbhat joined #gluster-dev
14:36 shyam joined #gluster-dev
15:04 gyadav joined #gluster-dev
15:15 nbalacha joined #gluster-dev
15:52 ashiq joined #gluster-dev
16:06 wushudoin joined #gluster-dev
16:06 wushudoin joined #gluster-dev
16:27 gyadav joined #gluster-dev
16:50 sanoj joined #gluster-dev
18:21 h4xr joined #gluster-dev
18:31 vbellur joined #gluster-dev
18:47 shyam joined #gluster-dev
19:13 cholcombe if i have an inode number does anyone know how i resolve that into a path with gfapi?
19:40 shyam joined #gluster-dev
19:44 cholcombe semiosis: ^^ ?
20:55 ira joined #gluster-dev
21:16 Acinonyx joined #gluster-dev
21:26 gem joined #gluster-dev

| Channels | #gluster-dev index | Today | | Search | Google Search | Plain-Text | summary